Hugging Face's logo

nvidia
/
Nemotron-4-340B-Instruct

NeMo
Model card Files Community
12
okuchaiev commited on
Commit
6d81254
•
1 Parent(s): a223205

Add files using large-upload tool

Browse files
Files changed (25) hide show
  1. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_17_96.pt +3 -0
  2. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_19_96.pt +3 -0
  3. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_30_96.pt +3 -0
  4. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_31_96.pt +3 -0
  5. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_32_96.pt +3 -0
  6. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_38_96.pt +3 -0
  7. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_39_96.pt +3 -0
  8. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_43_96.pt +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_45_96.pt +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_48_96.pt +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_4_96.pt +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_50_96.pt +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_59_96.pt +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_60_96.pt +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_61_96.pt +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_67_96.pt +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_68_96.pt +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_69_96.pt +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_77_96.pt +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_81_96.pt +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_82_96.pt +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_85_96.pt +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_90_96.pt +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_93_96.pt +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_9_96.pt +3 -0
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_17_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abcbc429045a564b70b5b8e6a3aebd65d5c9033d0851500eb76c099f47d78a95
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_19_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2f56efedb6748e4ff2a0e6a118ad77842e265a67f44e3f1448ce39549f7cc07
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_30_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91ceb57c7deb525d11d475ca2d983ac7fa9bdc652d3767e4466a7d2375007a37
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_31_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a0d4b9cdf13a1eba2ed93d85a2982360212cddc77d53c576022e3cbe189615f
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_32_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3ec2b18d724a72b6d794099f2440a62e2a76b0b343eb8562c7307923609080b
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_38_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed893da9981fc3c965691baa95bcb6d308b355cad5c450adc7446a4fbe8cd9cb
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_39_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b109bc001c35c681140f7729d952690a2e524e10f7f31b66473cd9368535724
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_43_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f67a153354d75feb672b47442b5b6b4e05a393ff95b9cf077bae7263f185230
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_45_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ea00ddac278ef7e34b6ec4802544a6b6204c661fcbb0682069f13b181042f3d
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_48_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb4e3686edebeef34059ccb1a24181f803157ce2fe1ad32327842e52f332f016
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_4_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:461f0daf5250e8e0f6a0d98a3936729d35c8fe255985e7824b06c8b5680cce96
3
+ size 1836
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_50_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:589423c313c3b3a1596305bef910e00c563ef1fcc0305777be0d8226cd391fdf
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_59_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:318589273676b17854619902806c202d0e2313dd0f9b335247e78421e3f8fee0
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_60_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae1b8b2fa8a86bf8650543a16b5ce2fedfe5225dbb442fcc74bbdc8d23365d42
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_61_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1e75f5e6cf3b5158698777317233c81b32327d4d64a20bed579a68da3d8df85
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_67_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5ba43e84b15cd21861c5c82b06043582e89234f1dd5a93a45433855d46acc16
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_68_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07033b70d349490e62e87c37b2c422207efe1e2411b575672ba110bc3c338d55
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_69_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3693816819b2ae665b43c0df95814b66c5d56af7f1fd8b5870887118b2ce0bf9
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_77_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ed64539a20733154f17cd57e606a3aab79606fa54fe7c7220cd57d79c6a5c43
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_81_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37af42582c2b74450e16a71bd80e24f762d3ffa8ac4599774d2a4a7a61820e6b
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_82_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d981dae8c5c3b6dad6c9f2fe25f26e4c445772ee9d9850c359b836ac8f6ae64
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_85_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc4edfcb2c11792b55ddf7c83de62c3bb26d09db3990f5e703c0a864bf1d9635
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_90_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1784707fcd135c45e6816dddceadc9820f25df2fb07797c61727ad5897929465
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_93_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c9154e83763b85c469f90fbd98d7d81388deca2aa97cdf867e343d61f026055
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_9_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aee04ee3a9964d7e6d305e5c1ad233bf6ef32b34178cda7bf7c2083c011e4e56
3
+ size 1836